Ultralytics
tasks/obb/ #7974
giscus[bot]
bot
Replies: 34 comments 102 replies
-
|
Hi, when I am using yolov8_obb model in results I always have even when the model makes prediction. Did someone faced with this problem and if yes, what was the solution? Thank you.🙂 |
Beta Was this translation helpful? Give feedback.
-
|
@kedardg absolutely, you can train OBB models like P2 or RTDETR from scratch even if they're not available pre-trained. You'd start by creating a new model from a YAML file, which defines the model architecture. Here's a quick example of how you might do it: yolo obb train data=your_dataset.yaml model=your_model.yaml epochs=100 imgsz=640Just replace |
Beta Was this translation helpful? Give feedback.
-
|
model = YOLO("yolov8n-obb.pt") i did this but i want to draw bounding boxes on the test image and return it. how to do that? my function is: def count_detection(image): |
Beta Was this translation helpful? Give feedback.
-
|
@RumaisaIlyas hey there! 😊 To draw bounding boxes on your test image and return it, you can use the def count_detection(image):
if image is not None:
# Load the YOLO model
model = YOLO('bestobbv8s.pt')
# Check the shape of the input image
print("Input image shape:", image.shape)
# Use the model to predict
results = model.predict(image)
# Draw bounding boxes and return the annotated image
annotated_image = results[0].plot()
# Count detections
count = len(results[0].obb)
print("count", count)
return annotated_imageIn this updated function, after making predictions with Let me know if you need further assistance! |
Beta Was this translation helpful? Give feedback.
-
|
thankyou so much for your assistance. i am facing a problem that my runs folder is not created after i run the code provided. why is that? what should i do in code so that i get the runs folder with my predicted image |
Beta Was this translation helpful? Give feedback.
-
|
Hey there! 😊 It sounds like you're doing everything right, but if the
from ultralytics import YOLO
# Load your model
model = YOLO('bestobbv8s.pt')
# Run prediction
results = model.predict('path/to/your/image.jpg')
# Save results
results.save() # This should automatically save your predictions in the 'runs' folder
results.save(save_dir='runs/detect') # Adjust the path as needed
If you've checked all these and the issue persists, it might be helpful to share more details about your environment (like your operating system) or any error messages you're seeing. That way, the community can offer more targeted advice. 🚀 Hope this helps, and happy detecting! |
Beta Was this translation helpful? Give feedback.
-
|
Hi, how can I access the results from this new model so I can extract bounding box information |
Beta Was this translation helpful? Give feedback.
-
|
Hey there! 😊 Accessing the results from a YOLOv8-OBB model to extract bounding box information is straightforward. After running predictions with your model, you can access the bounding boxes, class labels, and confidence scores directly from the from ultralytics import YOLO
# Load your YOLOv8-OBB model
model = YOLO('yolov8n-obb.pt') # For an official model
# model = YOLO('path/to/your/custom-model.pt') # Or load your custom trained model
# Run predictions on an image
results = model('path/to/your/image.jpg')
# Accessing bounding box information
for result in results:
boxes = result.boxes.xyxy # Bounding boxes in xyxy format
confs = result.boxes.conf # Confidence scores
classes = result.boxes.cls # Class labels
# Example: print bounding box info
for box, conf, cls in zip(boxes, confs, classes):
print(f"Box: {box}, Confidence: {conf}, Class: {cls}")This will print the bounding box coordinates, confidence scores, and class labels for each detection in your image. The bounding boxes are in the format Hope this helps! Let us know if you have any more questions. 🚀 |
Beta Was this translation helpful? Give feedback.
-
|
Ok so I've tried this and I'm getting the following error: boxes = result.boxes.xyxy # Bounding boxes in xyxy format |
Beta Was this translation helpful? Give feedback.
-
|
Hey there! 👋 It seems you're encountering an To fix this, first ensure your image path is correct and the image is accessible. Then, adjust detection thresholds or input image size if necessary, as these can impact detection performance. For accessing bounding boxes in an OBB model, you should use the # Ensure results is not None
if results[0] is not None:
obb_boxes = results[0].obb.xyxy # For OBB models
for obb_box in obb_boxes:
print(f"OBB Box: {obb_box}")
else:
print("No detections.")This snippet checks for detections before trying to access Hope this helps! Let me know if you have any other questions. 😊 |
Beta Was this translation helpful? Give feedback.
-
|
Hi，Could the heatmap functionality be used on YOLOv8-obb? |
Beta Was this translation helpful? Give feedback.
-
|
@huangjianxin38 hi! Yes, you can integrate heatmap functionality with YOLOv8-OBB models, although it might require some custom coding effort. The heatmap can usually be generated based on the final convolutional layer's outputs before the detection layer. While we don't have a ready-made function specifically for this in the documentation, you might look into visualizing the activation layers to get a sense of where the model is focusing within the OBB predictions. Here's a conceptual example of how you might approach this with PyTorch: from ultralytics import YOLO
import torch
# Load your YOLOv8-obb model
model = YOLO('yolov8n-obb.pt')
# Forward an image and get the features before the detection layer
img_path = 'path/to/your/image.jpg'
features = model.extract_features(img_path)
# Now, you can process 'features' to generate a heatmap
# This might include averaging across channels and applying a colormap
# Remember, this is just a conceptual guide. Details depend on your exact needs!Please, remember to check the model's structure ( Hope this helps! Feel free to reach out with any further questions. 🚀 |
Beta Was this translation helpful? Give feedback.
-
|
Hi,I have some questions when I use the DOTAv1.0 for OBB task. |
Beta Was this translation helpful? Give feedback.
-
|
Hey there! 👋 It looks like you need to format your results by category for the DOTA online server submission. While the direct For DOTA, your prediction file format typically should be: To generate predictions for each image and organize them by category, you could use something like this after your prediction step: predictions = model.predict('path/to/test/images')
for pred in predictions:
with open(f'results/{pred.image_name}.txt', 'w') as f:
for bbox in pred.boxes:
line = f"{pred.class_name} {bbox.conf} {bbox.x1} {bbox.y1} {bbox.x2} {bbox.y2} {bbox.x3} {bbox.y3} {bbox.x4} {bbox.y4}\n"
f.write(line)Then, to format for submission, organize these Quick Tip: DOTA might require a specific format for the filename or the way the data is zipped. Ensure to check their submission guideline for those details. 😉 Hope this helps, and good luck with your submission! 🚀 If you have more queries, feel free to drop them. |
Beta Was this translation helpful? Give feedback.
-
|
orig_shape: (1024, 1024) boxes: None the result of print like this, have no boxes for iteration? or and no confidence value in predict .txt files just having class label and eight index value(having been nomalized) , but DOTA online server fomat requirement is not nomalized index value |
Beta Was this translation helpful? Give feedback.
-
|
Hey there! 👋 It seems like you're encountering an issue with getting predictions in the required unnormalized format for DOTA submission and missing confidence scores. Let's tackle these issues:
Here's a snippet to adjust your predictions for submission: # Example: Convert normalized to absolute coordinates (unnormalized)
# Assuming 'pred' is your prediction object with normalized bbox corners
x1, y1, x2, y2, x3, y3, x4, y4 = pred['obb'] # normalized bbox corners
W, H = pred['orig_shape'] # Original image width and height
# Convert to absolute coordinates
x1, x2, x3, x4 = [x * W for x in [x1, x2, x3, x4]]
y1, y2, y3, y4 = [y * H for y in [y1, y2, y3, y4]]
# Ensure your prediction file includes confidence scores
confidence = pred['confidence']
# Format your prediction as per DOTA requirement (not normalized, includes confidence)
formatted_prediction = f"{pred['class_name']} {confidence} {x1} {y1} {x2} {y2} {x3} {y3} {x4} {y4}"For generating Each Hope this helps ease the process a bit! If anything remains unclear or if you encounter more hurdles, feel free to ask. Good luck with your submission! 🍀 |
Beta Was this translation helpful? Give feedback.
-
|
from ultralytics import YOLO def zip_predictions_folder(folder_path): zip_predictions_folder(sub_dir) i used this for generate DOTA online server format file ,but when i submit the result, the map is just 0.072, why |
Beta Was this translation helpful? Give feedback.
-
|
@hencai hey there! 🤗 It seems like your mAP score came out unexpectedly low. Here are a couple of things to check and some advice that might help improve your results:
For predictions not normalized and including the confidence score, here's an illustrative code adjustment: # Assuming 'pred' includes correct non-normalized detections
for pred in predictions:
box_list = pred.obb.xyxyxyxy.tolist() # Assuming these are non-normalized
confs = pred.obb.conf.tolist()
for i in range(len(pred.obb.cls)):
label = pred.names[pred.obb.cls[i]]
png_label = os.path.basename(pred.path).split('.')[0]
txt_file = os.path.join(sub_dir, f'{label}.txt') # Adjust to save by label names
box = ' '.join(map(str, [round(elem, 2) for sublist in box_list[i] for elem in sublist]))
conf = round(confs[i], 2)
with open(txt_file, 'a') as f:
f.write(f'{png_label} {conf} {box}\n')Remember, adapting to specific requirements, like unnormalized coordinates and including confidence scores, is key for successful DOTA submissions. Hope this helps! Feel free to reach out if you have more questions. Best of luck with your next submission! 😊 |
Beta Was this translation helpful? Give feedback.
-
|
how to do Model Ensembling on yolov8-obb models？ |
Beta Was this translation helpful? Give feedback.
-
|
Model ensembling with YOLOv8-obb models involves combining the predictions from multiple trained models to improve the accuracy of your oriented objects detection. Currently, direct support for model ensembling within Ultralytics YOLO isn't provided out-of-the-box. However, you can manually implement ensembling by running predictions with each model separately and then combining these predictions. One common approach is to average the bounding box coordinates and confidence scores of the same object detected by multiple models. Ensure to consider the rotating angle parameter unique to OBB models in your ensembling logic. Here's a basic conceptual example to get you started: from ultralytics import YOLO
models = [
YOLO('path/to/first_obb_model.pt'),
YOLO('path/to/second_obb_model.pt'),
# Add more models as needed
]
# Assuming you have a method to read your images/videos
image = 'path/to/image.jpg'
# List to store results from all models
all_preds = []
for model in models:
results = model(image)
all_preds.append(results.pandas().xyxy[0]) # Extracting predictions
# Assuming you have a method `combine_predictions(all_preds)`
# that combines predictions from all models
final_predictions = combine_predictions(all_preds)
# Process `final_predictions`...This example loads each model, runs predictions on the same image, and stores the results. You'd then need to implement Remember, ensembling may increase inference time due to processing with multiple models. Always weigh the benefits of improved accuracy against potential increases in computational cost. Happy coding! 😊 |
Beta Was this translation helpful? Give feedback.
-
|
Hi, the YOLOv8n-obb test map-50 result on DOTAv1.0 is 78.0%. I split the train set and val set images to 1024*1024 and I wonder the 78% is the val set result given by the model.val()? or the test set result given by the DOTA server? And how to merge the result submitted to the server if the figure 78% is the test result given by the DOTA server? |
Beta Was this translation helpful? Give feedback.
-
|
Thank you very much for your suggestion. I can successfully submit the results to the official website of the Dota dataset. However, my training method involves cutting single scale images, all of which are 1024 in size. Using your OBB pre trained model weights, why did I only achieve an accuracy of 49% of the map on the test set when training 100 epochs? It is because of the size of my images? Can YOLO only cut 640 training or for other reasons? Note that I am training at a single scale, and the results on your official website are all training results under multi-scale cutting. I would like to know how many epochs need to be trained to achieve the accuracy of your official website? model = YOLO('/xiaying_ms/bp/Large-Selective-Kernel-Network/tools/yolov8/yolov8n-obb.yaml').load('/xiaying_ms/bp/Large-Selective-Kernel-Network/tools/yolov8/yolov8n-obb.pt') # build from YAML and transfer weights Train the model with 2 GPUsresults = model.train(data='/xiaying_ms/bp/Large-Selective-Kernel-Network/tools/yolov8/dotav1.yaml', |
Beta Was this translation helpful? Give feedback.
-
|
Hey there! Achieving a lower mAP (49%) compared to the official results (78% for YOLOv8n-obb on DOTAv1.0) could indeed be influenced by the single-scale training approach. Here are some suggestions:
As for the code snippet you provided, it looks like you're on the right track. Perhaps try adapting it to use variable image sizes for training: from ultralytics import YOLO
# Load the model
model = YOLO('yolov8n-obb.yaml').load('yolov8n-obb.pt')
# Train with varied image sizes
results = model.train(data='dotav1.yaml', epochs=100, imgsz=[640, 1024], device=[0, 1])Note: Keep experimenting, and good luck! 🍀 |
Beta Was this translation helpful? Give feedback.
-
|
But currently, my images only have 1024 sized single scale images that have been cut, and I am using them for comparative experiments. Is the official results (78% for YOLOv8n obb on DOTAv1.0) you just mentioned the official results for single scale? I couldn't find it on the official website. How many epochs are 78% of this website trained under what image size? |
Beta Was this translation helpful? Give feedback.
-
|
Hey there! 😄 It looks like you're diving deep into using the YOLOv8n-obb model for oriented bounding box detection on the DOTA dataset. You've noticed a significant point regarding single-scale versus multi-scale training which can indeed have a big impact on your model's performance. The official 78% mAP for YOLOv8n-obb mentioned on our website is achieved under multi-scale training conditions, typically with image sizes around 1024 pixels. This diversity in image sizes during training plays a crucial role in making the model more resilient and adaptable to various object sizes, which is likely why you're seeing a difference in accuracy with single-scale training. If you're sticking to 1024-sized single-scale images for your comparison experiments, it's worth considering incorporating multi-scale training to better match the conditions under which the official results were obtained. As for the epochs, the official results are generally achieved after extensive hyperparameter tuning and potentially more than 100 epochs of training, depending on various factors like the complexity of the dataset, learning rate schedules, etc. Here’s a little adjustment to your training code that enables multi-scale training: from ultralytics import YOLO
# Load the model with pre-trained weights
model = YOLO('yolov8n-obb.yaml').load('yolov8n-obb.pt')
# Train the model with multi-scale
results = model.train(data='dotav1.yaml', epochs=100, imgsz=[640, 1024], device=[0, 1])Remember, achieving top-notch results often requires experimenting with not just epochs and image sizes but also with learning rates, batch sizes, and augmentation strategies. Keep exploring, and best of luck! 🚀 If you have any more questions or need further assistance, feel free to ask. |
Beta Was this translation helpful? Give feedback.
-
|
@hencai Hi I notice that you can train yolov8_obb models on muti-GPUs, how can you achieve this? Did you enconunter this error? File "/tmp/pycharm_project_538/ultralytics-main/ultralytics/utils/loss.py", line 626, in call |
Beta Was this translation helpful? Give feedback.
-
|
how can i test DOTA1.0 datasets using YOLOV8-obb ? online submit for results? somebody help me? emergency |
Beta Was this translation helpful? Give feedback.
-
|
@hencai hey there! 🌟 For testing DOTA1.0 datasets using YOLOv8-obb, you can follow these steps:
If this is an emergency, I'd recommend diving into the predict and val sections of the documentation for detailed code examples and further instructions. The key here is to ensure your dataset is correctly formatted as per the Dataset Guide and utilize the pretrained models effectively. For submitting your results, please check the specific instructions provided by DOTA1.0 on their evaluation server. Every competition or dataset may have a slightly different submission procedure. Hope this helps, and good luck with your work! |
Beta Was this translation helpful? Give feedback.
-
|
Hi, I saw yolov8 obb with tracking from yolov8-v2 |
Beta Was this translation helpful? Give feedback.
-
|
Hey there! 🚀 It looks like you're interested in the YOLOv8 Oriented Bounding Boxes (OBB) model with tracking. For comprehensive documentation on YOLOv8 OBB, including details on training, validating, making predictions with, and exporting these models, you can check out our dedicated Oriented Bounding Boxes Object Detection page. You'll find everything from an introduction to oriented object detection, tips on using the YOLOv8 OBB models (which are pretrained on DOTAv1 and use the from ultralytics import YOLO
# Load a YOLOv8n-obb model
model = YOLO('yolov8n-obb.pt') # Load a pretrained model
# Train the model
results = model.train(data='dota8.yaml', epochs=100, imgsz=640)And for validation: # Validate the model
metrics = model.val(data='dota8.yaml')Feel free to explore the page for more details on other tasks like exporting models to different formats! If you have any further questions, just let me know. Happy detecting! |
Beta Was this translation helpful? Give feedback.
-
|
Subject: Cropping Images from YOLOv8 Detections (Python) Hi everyone, I'm working on a Python project that utilizes a YOLOv8 model for object detection. I'd like to achieve the following functionality: Perform object detection on input images using my trained YOLOv8 model. could you share an example code snippet demonstrating how to achieve this cropping functionality using the bounding box data? |
Beta Was this translation helpful? Give feedback.
-
|
Hey there! 👋 For cropping images using bounding box information from YOLOv8 detections, you can follow this straightforward example. Once you've got the detection results, you can simply loop through them, access the bounding box coordinates, and use them to crop the original image. Here's how: from PIL import Image
from ultralytics import YOLO
# Load your trained model
model = YOLO('path/to/your_model.pt')
# Run detection
results = model('path/to/input/image.jpg')
# For each detection, crop and save the image
for i, det in enumerate(results[0].boxes.xyxy):
# Convert detections to integer coordinates
xmin, ymin, xmax, ymax = map(int, det[:4])
# Open the original image
img = Image.open('path/to/input/image.jpg')
# Crop the image based on detection bounding box
cropped_img = img.crop((xmin, ymin, xmax, ymax))
# Save the cropped image
cropped_img.save(f'cropped_image_{i}.jpg')This script will save each detected object as a separate cropped image. Make sure to replace Happy coding! 🚀 |
Beta Was this translation helpful? Give feedback.
-
|
Hello, I'm currently working with YOLOOBB (You Only Look Once Oriented Bounding Boxes), and I've annotated my data using the YOLOOBB format. My concern now is how to apply augmentations for oriented bounding boxes, particularly for transformations like rotation, horizontal flipping, and vertical flipping. Each augmented image will need its annotation file adjusted accordingly. I'm using the albumentations library in Python for data augmentation. Here's the transformation pipeline I've defined: import albumentations as A
transform_pipeline= A.Compose([
A.Rotate(limit=(-90, 90)),
A.VerticalFlip(p=1),
A.HorizontalFlip(p=0.5),
A.ToTensor()
], bbox_params=A.BboxParams(
format="yolo",
label_fields=["class_labels"],
))However, the YOLOOBB format is different from the default YOLO format. How should I process the annotations in this case to ensure they match the augmented images? Any insights or suggestions on how to handle this scenario would be greatly appreciated! Thank you. |
Beta Was this translation helpful? Give feedback.
-
|
Hey there! It looks like you're taking on the challenge of data augmentation for YOLOOBB, which is super interesting. 🚀 When dealing with rotations and flips, especially with oriented bounding boxes (OBBs), the key lies in adjusting the angle of orientation alongside the bounding box coordinates during augmentation. For albumentations, you're on the right track with defining transformations. However, for YOLOOBB which includes angles in annotations, you'll need to handle the angle adjustments manually post-augmentation, as albumentations currently doesn't directly support the YOLOOBB format with angle orientation. After applying the transformations, you can adjust the angle as follows:
Since these are post-processing steps after albumentations' transformations, you would iterate through each transformed bounding box and apply the corresponding angle adjustments according to the transformation applied. Given the complexity, you might consider writing or modifying a custom function in your dataset processing pipeline that applies these post-augmentation corrections to ensure the augmented annotations remain consistent with their respective images. Keep in mind, this approach requires careful implementation to make sure angles are adjusted correctly, taking into account the periodic nature of angles (e.g., handling cases where angle exceeds 360 degrees or goes below 0). def adjust_obb_annotations(boxes, transformation_type, transformation_value):
# Your code here to adjust the angles and bounding boxes
passThis isn't a one-size-fits-all solution, and experimentation may be necessary to tailor the adjustments to your specific dataset and augmentation needs. I hope this helps give you a direction on handling OBBs with your augmentations! Feel free to reach out if you have more questions or need further assistance. Happy coding! 🚀 |
Beta Was this translation helpful? Give feedback.
-
|
HI, when I am training yolov8_obb models on muti-GPUs I meet an error File "/tmp/pycharm_project_538/ultralytics-main/ultralytics/utils/loss.py", line 626, in call It seems that the error is related to the calculation of the OBB loss. It expects two elements but got three. This error occurs when training on multiple GPUs, but it works fine on single GPU. How can I solve this problem?Thank you. |
Beta Was this translation helpful? Give feedback.
-
|
@ccsadsxz hey! 👋 It looks like you're diving into YOLOv8 OBB (Oriented Bounding Boxes) models, which is great for detecting objects with more accuracy by considering their orientation. You're already on the right track by exploring our docs and examples. For your quick reference, here are a few points that might help you further:
Here's a snippet to get you started with model export after training: model = YOLO('yolov8n-obb.pt') # Assuming yolov8n-obb.pt is your trained model
model.export(format='onnx') # Export to ONNX formatIf you run into any further issues or have questions about OBB specific details, feel free to reach out. Happy coding! 🚀 |
Beta Was this translation helpful? Give feedback.
-
|
@ccsadsxz I am getting a similar RuntimeError to you, were you able to correctly resolve this? |
Beta Was this translation helpful? Give feedback.
-
|
@glenn-jocher , I am confused, why did you say "To train on OBB datasets, ensure your dataset is properly formatted. For OBB, you'll need five values [x_center, y_center, width, height, angle] for each bounding box.". I thought the expected format is "class_index, x1, y1, x2, y2, x3, y3, x4, y4" ? |
Beta Was this translation helpful? Give feedback.
-
|
Hey! 👋 You brought up a great point regarding the format for OBB datasets. The essential distinction here is between the handling of conventional bounding boxes and the oriented bounding boxes (OBB). For conventional YOLO models, the dataset format usually includes In the context of Ultralytics YOLO, for OBB, a typical input might also include an angle along with the center coordinates and dimensions (i.e., If there's any specific documentation or part of the dataset you're following, it's a good practice to stick closely to those format guidelines. Always open to discussing this further if you have more insights or queries! 🚀 |
Beta Was this translation helpful? Give feedback.
-
|
@SilverStarCoder Sorry, I still haven't solved this problem. |
Beta Was this translation helpful? Give feedback.
-
|
i am curious, doest it uses the same approach as yolov5-obb which use CSL for its OBB function? |
Beta Was this translation helpful? Give feedback.
-
|
@Violet-R4iN hey there! 😊 The YOLOv8 Oriented Bounding Boxes (OBB) models, identified by the For example, to use one of these models for detection, you'd load and predict like so: from ultralytics import YOLO
# Load the OBB model
model = YOLO('yolov8n-obb.pt')
# Predict!
results = model('https://ultralytics.com/images/bus.jpg')Feel free to explore this feature for tasks requiring more detailed object localization. 🚀 |
Beta Was this translation helpful? Give feedback.
-
Beta Was this translation helpful? Give feedback.
-
|
@SFSimDev hey there! To save your OBB results as GeoJSON after running a YOLOv8 model against a GeoTIFF and preserve the coordinates, you might consider using Python libraries like
Here's a small code snippet to illustrate parts of this process: import rasterio
from geojson import Feature, Point, FeatureCollection
import json
# Load GeoTIFF and model results (pseudo-code)
with rasterio.open('path/to/your/geotiff.tif') as src:
affine = src.transform
# Assume 'results' is your model's output in pixel coords
# Convert results to GeoJSON (pseudo-code, simplify as needed)
features = []
for res in results:
geo_point = affine * (res.x, res.y) # Convert pixel coords to geo coords
point = Point((geo_point[0], geo_point[1]))
features.append(Feature(geometry=point, properties={"class": res.class, "confidence": res.confidence}))
# Save to GeoJSON
feature_collection = FeatureCollection(features)
with open('detections.geojson', 'w') as f:
json.dump(feature_collection, f)Keep in mind this is a high-level approach, and you'd need to adjust and extend it based on your exact requirements and the structure of your detection results. Also, make sure to manage the conversion between the coordinate systems accurately to retain the geographical accuracy of your results. Hope this helps you on your geospatial adventure! 🚀 |
Beta Was this translation helpful? Give feedback.
-
|
Hi @pderrenger - Thanks this seems to be pretty much what I'm after but for some reason I'm getting the following error:
Do you know why this might be happening? I've tried running it with my own model and the pretrained yolov8x-obb.pt plus a couple of different geotiff images on separate runs. I appreciate any help you can provide. |
Beta Was this translation helpful? Give feedback.
-
|
Hi @SFSimDev, It looks like the error Here's how you can modify your code to correctly access the bounding box coordinates: from ultralytics import YOLO
# Load your model
model = YOLO('yolov8x-obb.pt')
# Run prediction
results = model('path/to/your/image.jpg')
# Access bounding box coordinates
for result in results:
for box in result.boxes:
x_center, y_center, width, height, angle = box.xywha # x_center, y_center, width, height, angle
print(f'Center: ({x_center}, {y_center}), Width: {width}, Height: {height}, Angle: {angle}')Make sure to replace Let me know if this helps or if you have any more questions! 😊 |
Beta Was this translation helpful? Give feedback.
-
|
for yolov8n-obb , results[0].boxes are returning none. previously, it was working. i think ultralytics recent update got it removed? |
Beta Was this translation helpful? Give feedback.
-
|
Hey there! 🌟 It sounds like you're encountering an issue with the Could you please ensure you're loading the model correctly with the latest version? Here's a quick snippet you can try: from ultralytics import YOLO
# Load the YOLOv8n-obb model
model = YOLO('yolov8n-obb.pt')
# Run prediction and check boxes
results = model('path/to/image.jpg')
if results[0].boxes is not None:
print("Boxes are detected!")
else:
print("No boxes detected, please check your model or image.")If the problem persists, kindly share a bit more detail on the steps you followed or any specific changes in your environment. 🛠 Our team is here to help get to the bottom of this! |
Beta Was this translation helpful? Give feedback.
-
|
I'm not the OP but I'm seeing the same error. I have added to the code to show that there are results but that results[0].boxes isn't working as expected. Output: |
Beta Was this translation helpful? Give feedback.
-
|
@SFSimDev hey there! It seems like there might be a slight misunderstanding related to the output of From the output you've shared, it's clear that the model is recognizing and processing the image correctly as it should. However, for oriented bounding boxes (OBB), the results are stored in the For accessing the oriented bounding boxes, simply replace from ultralytics import YOLO
# Load the YOLOv8n-obb model
model = YOLO('yolov8n-obb.pt')
# Run prediction and check boxes
results = model('boats.tiff')
if results[0].obb is not None: # Access the .obb attribute instead of .boxes
print("Oriented bounding boxes are detected!")
else:
print("No oriented bounding boxes detected, please check your model or image.")Give this a try, and it should access the detected oriented bounding boxes as expected. Keep up the great work! 🌟 |
Beta Was this translation helpful? Give feedback.
-
|
Hey, 0: 704x1024 191.9ms AttributeError: 'NoneType' object has no attribute '_jit_internal' This is my code: cap = cv2.VideoCapture("video.mp4") while True: |
Beta Was this translation helpful? Give feedback.
-
|
@lamb412 hi there, It looks like the error you're encountering is due to the First, ensure that the video content contains objects that the OBB model is trained to detect, and check the lighting or image quality. As a quick fix, you can add a check to see if for r in results:
boxes = r.boxes
if boxes is not None: # Add this check
for box in boxes:
x1, y1, x2, y2 = box.xyxy[0]
x1, y1, x2, y2 = int(x1), int(y1), int(x2), int(y2)
# your remaining logicThis should prevent your program from crashing when no objects are detected. If the issue persists, consider tuning the model or revisiting the training dataset to ensure it aligns well with your video content. Hope this helps! If you need further assistance, feel free to ask. 😊 |
Beta Was this translation helpful? Give feedback.
-
|
How to use webcam in yolov8 obb ? |
Beta Was this translation helpful? Give feedback.
-
|
Hey there! To use a webcam with the YOLOv8 OBB (Oriented Bounding Boxes) model, you can modify your from ultralytics import YOLO
import cv2
# Load OBB model
model = YOLO('yolov8n-obb.pt') # Adjust path if needed
# Start webcam capture
cap = cv2.VideoCapture(0) # '0' assumes the default webcam
while True:
ret, frame = cap.read()
if not ret:
break
# Predict using the OBB model
results = model.predict(frame)
# Visualize results
frame = results.render()[0]
cv2.imshow('YOLOv8 OBB Webcam', frame)
if cv2.waitKey(1) == ord('q'): # Press 'q' to quit
break
cap.release()
cv2.destroyAllWindows()In this script, |
Beta Was this translation helpful? Give feedback.
-
|
Can I use this feature with the Raspberry Pi 5's PiCamera3? |
Beta Was this translation helpful? Give feedback.
-
|
@tjsgn hello! 👋 Yes, you can definitely use the YOLOv8 Oriented Bounding Boxes (OBB) feature with the Raspberry Pi 5's PiCamera3. The Raspberry Pi 5, with its improved processing power, should be capable of running YOLOv8 models, although you might need to optimize the model for better performance due to the limited resources compared to more powerful hardware. Here's a step-by-step guide to get you started:
Feel free to experiment with different configurations and optimizations to find the best setup for your use case. If you run into any issues or have more questions, the YOLO community and the Ultralytics team are here to help! 😊 Happy coding and good luck with your project! 🚀 |
Beta Was this translation helpful? Give feedback.
-
|
I am new to YOLOV8 OBB. I have used mask and detection before. I have already trained a large obb model on custom dataset. I want to test it now and I want the bounding box to be rotated as per the object and provide me the angle of rotation and the center coordinate of the detected object. I would also really appreciate if you could provide me the code for that. I will want to use this format: xywhr Thank you |
Beta Was this translation helpful? Give feedback.
-
|
@BhargavNGali hello! Welcome to the world of YOLOv8 OBB! It's great to hear that you've successfully trained a large OBB model on your custom dataset. To test your model and obtain the rotated bounding boxes in the Python Examplefrom ultralytics import YOLO
# Load your trained model
model = YOLO("path/to/your/custom_model.pt")
# Predict with the model
results = model("path/to/your/test_image.jpg")
# Extract the rotated bounding boxes in xywhr format
for result in results:
for box in result.obb.xywh:
x, y, w, h, r = box # x, y are the center coordinates, w and h are width and height, r is the rotation angle
print(f"Center: ({x}, {y}), Width: {w}, Height: {h}, Rotation: {r}")CLI Exampleyolo obb predict model=path/to/your/custom_model.pt source='path/to/your/test_image.jpg'This will provide you with the center coordinates, width, height, and rotation angle for each detected object. If you encounter any issues or need further assistance, please ensure you are using the latest versions of pip install --upgrade torch ultralyticsFor more detailed information on oriented bounding boxes, you can refer to our Oriented Bounding Boxes Object Detection documentation. Happy coding! 😊 |
Beta Was this translation helpful? Give feedback.
-
|
Hello, I have some questions about the OBB detection codes in tal.py/dist2rbox. |
Beta Was this translation helpful? Give feedback.
-
|
@dlwforever hello, Thank you for your question regarding the OBB detection codes in
For a more detailed, line-by-line annotation, it would be helpful if you could provide a snippet of the code you're working with. This will allow us to give you a more precise and tailored explanation. Additionally, please ensure you are using the latest version of the Ultralytics repository, as updates may include improvements or clarifications that could resolve your queries. For further reading and examples, you can refer to the Oriented Bounding Boxes Object Detection documentation. Feel free to share the specific code snippet you need help with, and we’ll be happy to assist you further! 😊 |
Beta Was this translation helpful? Give feedback.
-
|
def dist2rbox(pred_dist, pred_angle, anchor_points, dim=-1): The above code is about the decode part. I don't know the variables "xf" and "yf" meaning and how to understand the transform from xf, yf to x, y. Could you give the illustration about the question? |
Beta Was this translation helpful? Give feedback.
-
|
@dlwforever hello! Thank you for your detailed question regarding the In the context of the lt, rb = pred_dist.split(2, dim=dim)
xf, yf = ((rb - lt) / 2).split(1, dim=dim)Here, Next, the transformation to cos, sin = torch.cos(pred_angle), torch.sin(pred_angle)
x, y = xf * cos - yf * sin, xf * sin + yf * cosIn this step:
Finally, these rotated distances ( xy = torch.cat([x, y], dim=dim) + anchor_pointsThe function then concatenates these center coordinates with the original distances to form the complete bounding box representation: return torch.cat([xy, lt + rb], dim=dim)This results in the predicted rotated bounding boxes. I hope this explanation clarifies the transformation process. If you have any further questions or need additional details, feel free to ask! 😊 For more information, you can also refer to the Ultralytics documentation on Oriented Bounding Boxes. |
Beta Was this translation helpful? Give feedback.
-
|
Thanks for your reply. I think I understand the code meaning. |
Beta Was this translation helpful? Give feedback.
-
|
You're welcome! I'm glad to hear that the explanation helped clarify the code for you. 😊 For further insights into Oriented Bounding Boxes (OBB) and their applications, you might find the Oriented Bounding Boxes Object Detection section of our documentation particularly useful. It provides comprehensive details on how to train, validate, and use OBB models with YOLOv8, including examples and dataset formats. If you have any more questions or need additional assistance, feel free to ask. Happy coding! 🚀 |
Beta Was this translation helpful? Give feedback.
-
about the test mAP, How do you merge the result? and what's the nms_threshold?How do you merge the result to submit to DOTA server? since I can't find a merge script in YOLO repo, I write it based on the merge_result function in MMRotate, and use nms threshold =0.1, I can only get about 78ppt on YOLOv8m, which is about 2 ppt lower than you published. |
Beta Was this translation helpful? Give feedback.
-
|
I don't know if I'll get a notification when be replied, if not, please address me at tianlhcs@163.com |
Beta Was this translation helpful? Give feedback.
-
|
@tianlianghai hi there, Thank you for your question regarding the merging of results for submission to the DOTA server and the NMS threshold settings. To achieve the best results when merging predictions for DOTA evaluation, it's crucial to use an appropriate Non-Maximum Suppression (NMS) threshold. Based on our experience, a common NMS threshold for DOTA is around 0.1, which you have already implemented. However, achieving the published mAP values also depends on other factors such as the exact implementation of the merging script and the specific settings used during validation. Here are some steps to ensure optimal results:
Here is a sample code snippet for running validation and merging results: from ultralytics import YOLO
# Load the model
model = YOLO("yolov8m-obb.pt")
# Validate the model
metrics = model.val(data="dota8.yaml")
# Access the mAP metrics
print(f"mAP50-95: {metrics.box.map}")
print(f"mAP50: {metrics.box.map50}")
print(f"mAP75: {metrics.box.map75}")For more detailed guidance on oriented bounding boxes and the DOTA dataset, you can refer to our Oriented Bounding Boxes Object Detection documentation. If you continue to face issues, please share more details or your reproducible example, and we will be happy to assist further. |
Beta Was this translation helpful? Give feedback.
-
|
The documentation has given a mAP_test(50) of 78.0 for YOLOv8n-obb. z But when I submit it on DOTAv1 Task1 Server, I get a result of only 50.8, what is the reason for this? Is there something wrong with my format conversion code? my code as follows： file_names = { Assuming yolov8n-obb.pt is your trained modelmodel = YOLO('/xiaying_ms/bp/Large-Selective-Kernel-Network/runs/obb/train10/weights/best.pt') for i in file_names: for pred in predictions: def zip_predictions_folder(folder_path): zip_predictions_folder(sub_dir) Can you please help me check what's wrong? Or what is it that is causing this? Thank you very much. |
Beta Was this translation helpful? Give feedback.
-
|
Can you guys provide a copy of the official code that transforms DOTA v1 Task1 Server and evaluation settings (e.g., confidence thresholds, IoU thresholds),I would like to be able to reproduce, the official documentation on yolov8n-obb on the test set The mAP is 78.5.thank you! |
Beta Was this translation helpful? Give feedback.
-
|
Hi @CS-Guo, Thank you for your question! To help you reproduce the mAP of 78.0 for YOLOv8n-OBB on the DOTAv1 test set, it's essential to ensure that your evaluation settings and format conversions are correct. Official Code and Evaluation SettingsWhile we don't provide direct access to the internal evaluation scripts used on the DOTAv1 Task1 Server, you can follow these steps to ensure your setup aligns with the official evaluation:
Example Code for Predictions and SubmissionsHere's a refined version of your code to ensure proper format and submission: import os
import zipfile
from ultralytics import YOLO
file_names = {
0: 'Task1_plane.txt',
1: 'Task1_ship.txt',
2: 'Task1_storage-tank.txt',
3: 'Task1_baseball-diamond.txt',
4: 'Task1_tennis-court.txt',
5: 'Task1_basketball-court.txt',
6: 'Task1_ground-track-field.txt',
7: 'Task1_harbor.txt',
8: 'Task1_bridge.txt',
9: 'Task1_large-vehicle.txt',
10: 'Task1_small-vehicle.txt',
11: 'Task1_helicopter.txt',
12: 'Task1_roundabout.txt',
13: 'Task1_soccer-ball-field.txt',
14: 'Task1_swimming-pool.txt'
}
# Load the trained model
model = YOLO('/xiaying_ms/bp/Large-Selective-Kernel-Network/runs/obb/train10/weights/best.pt')
predictions = model.predict('xwp_data/DOTA-v1.0/test/images', save_txt=True)
txt_path = '/home/zzheng/gsf/ultralytics/runs/obb/predict10'
sub_dir = os.path.join(txt_path, 'submission')
os.makedirs(sub_dir, exist_ok=True)
# Initialize empty files
for i in file_names:
create_txt_path = os.path.join(sub_dir, file_names[i])
with open(create_txt_path, "w") as file:
file.write('')
# Write predictions to files
for pred in predictions:
box_list = pred.obb.xyxyxyxy.tolist() # Assuming these are non-normalized
confs = pred.obb.conf.tolist()
for i in range(len(pred.obb.cls)):
png_label = os.path.basename(pred.path)[:5]
txt_file = os.path.join(sub_dir, file_names[int(pred.obb.cls[i])])
box = ' '.join(map(str, [round(elem, 2) for sublist in box_list[i] for elem in sublist]))
conf = round(confs[i], 2)
with open(txt_file, 'a') as f:
f.write(f'{png_label} {conf} {box}\n')
# Zip the predictions folder
def zip_predictions_folder(folder_path):
if not os.path.exists(folder_path):
print(f"Folder '{folder_path}' does not exist.")
return
zip_file_name = "predictions.zip"
with zipfile.ZipFile(os.path.join(txt_path, zip_file_name), "w") as zipf:
for foldername, subfolders, filenames in os.walk(folder_path):
for filename in filenames:
file_path = os.path.join(foldername, filename)
zipf.write(file_path, os.path.relpath(file_path, folder_path))
print(f"Folder '{folder_path}' has been zipped and saved as '{zip_file_name}'.")
zip_predictions_folder(sub_dir)Additional ResourcesFor more detailed information on OBB datasets and format conversions, you can refer to the Oriented Bounding Box (OBB) Datasets Overview. If you continue to experience issues, please ensure you are using the latest versions of the Ultralytics packages and provide a reproducible example so we can assist you further. Best of luck with your evaluation, and feel free to reach out if you have any more questions! 😊 |
Beta Was this translation helpful? Give feedback.
-
|
Submit data to the DOTA server. The model predictions should be made on 1024x1024 test set images. The results of the predictions should then be merged back into the original image. Do not directly pass the original test set images into the model. The dota_devkit library has some methods that can help achieve this. |
Beta Was this translation helpful? Give feedback.
-
|
I also need this kind of code, but I don't have the time or coding skills. If you could share the completed code, I would be very grateful. |
Beta Was this translation helpful? Give feedback.
-
|
Thank you for your interest. While we can't provide completed code, the Ultralytics documentation offers detailed guidance on using YOLOv8-OBB models, including training, validation, and prediction. You can find more information on the Oriented Bounding Boxes Object Detection page. If you encounter specific issues or need further assistance, feel free to ask! |
Beta Was this translation helpful? Give feedback.
-
|
yolo val obb data=DOTAv1.yaml device=0 split=test |
Beta Was this translation helpful? Give feedback.
-
|
@XWP-PPP the command |
Beta Was this translation helpful? Give feedback.
-
|
Hi, I'd like to ask about training YOLOv8 OBB. Using this command Thank you. |
Beta Was this translation helpful? Give feedback.
-
|
@jeffrymahbuubi using |
Beta Was this translation helpful? Give feedback.
-
|
Hi, thank you for the answer, but during training it use the # Python Script Version
from ultralytics import YOLO
model = YOLO("yolov8-obb.yaml").load("yolov8n-obb.pt") # build from YAML and transfer weights
# Configuration
imgsz = 640
epochs = 100
batch = 8
workers = 4
cache = False
YAML_FILE = "dota8.yaml"
name = "yolov8n-obb"
project = "obb"
device = 0
exist_ok = True
# Train the model
results = model.train(
data=YAML_FILE,
device=device,
epochs=epochs,
imgsz=imgsz,
batch=batch,
cache=cache,
project=project,
name=name,
patience=50,
augment=False,
exist_ok=exist_ok,
workers=workers
)The WARNING no model scale passed. Assuming scale='n'.
Transferred 361/397 items from pretrained weights
Downloading https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8n.pt to 'yolov8n.pt'... |
Beta Was this translation helpful? Give feedback.
-
|
@jeffrymahbuubi thank you for providing the details. It seems that the model is downloading from ultralytics import YOLO
# Load the pretrained YOLOv8n-OBB model
model = YOLO("yolov8n-obb.pt")
# Train the model
results = model.train(
data="dota8.yaml",
epochs=100,
imgsz=640,
batch=8,
workers=4,
cache=False,
project="obb",
name="yolov8n-obb",
device=0,
exist_ok=True
)This should ensure that the correct OBB-specific weights are used for training. If the issue persists, please verify that the |
Beta Was this translation helpful? Give feedback.
-
|
It appears that the model is still downloading |
Beta Was this translation helpful? Give feedback.
-
|
Hello, when I used obb to train a slender frame similar to 2150x200 on an image of size 5120x5120, the training size was 1024, and the pre-training weight was obb-m. I trained for 300 eopches, but the final verification result had a very low confidence. Low, almost all 0.4, and the size of many prediction boxes is only about 500x200. How should I solve it? |
Beta Was this translation helpful? Give feedback.
-
|
@LiangChaoWei512 hello, it sounds like the low confidence and small prediction box sizes might be due to a few factors. First, ensure you are using the latest version of the Ultralytics package. Next, consider adjusting the image size and batch size to better fit your dataset. You might also want to fine-tune the learning rate and other hyperparameters. Additionally, check if your dataset annotations are accurate and consistent. For more detailed guidance, you can refer to the Ultralytics OBB documentation. If the issue persists, please provide more details about your training setup. |
Beta Was this translation helpful? Give feedback.
-
|
from ultralytics import YOLO if name == 'main': This is my training parameter setting |
Beta Was this translation helpful? Give feedback.
-
|
Thanks for sharing your training parameters. Given the low confidence and small prediction box sizes, I recommend checking a few things:
If the issue persists, please provide more details about your dataset and training setup. For additional guidance, refer to the Ultralytics OBB documentation. |
Beta Was this translation helpful? Give feedback.
-
|
Please tell me how to adjust the learning rate and hyperparameters.thanks！ |
Beta Was this translation helpful? Give feedback.
-
|
To adjust the learning rate and other hyperparameters, you can modify the |
Beta Was this translation helpful? Give feedback.
-
|
Dear YOLOv8 Team, I am working on a snake classification project and using YOLOv8 for both object detection and classification tasks. I have encountered a couple of questions and would appreciate your guidance. Cropping and Classifying Images: I am currently using YOLOv8 for object detection with the following code snippet to crop images: This code successfully crops images. However, instead of saving these cropped images, I want to pass them directly to the classification model within the same script. Current Classification Process: Goal: Could you please provide guidance on how to efficiently combine the object detection and classification processes within the same script? Thank you for your assistance. Best regards, |
Beta Was this translation helpful? Give feedback.
-
|
Hello! When I used 'xywhr' to get the angle of rotation, the angle range was only 0 to 180 degrees, which could not distinguish between the head and the tail of the object being detected. What should I have to do to get an angle from 0 to 360 degrees? Or by what means can I distinguish between the head and the tail of an object? This is an urgent question for me. I would appreciate it if you could answer it for me. |
Beta Was this translation helpful? Give feedback.
-
|
@reizzzzz hello, To distinguish between the head and tail of an object and obtain an angle from 0 to 360 degrees, you need to modify the angle calculation. The standard For more detailed guidance on handling oriented bounding boxes and angle calculations, please refer to our documentation at https://docs.ultralytics.com/tasks/obb/. This resource provides comprehensive information on working with OBBs in Ultralytics YOLO models. |
Beta Was this translation helpful? Give feedback.
-
|
Hello! I'm trying to reproduce the mAP50 results on the DOTA test set. In the above table, yolov8n-obb achieves 78 mAP on the DOTA test set, but I only get 71.62 on the DOTA evaluation server. My evaluation steps are :1. split the test set images into 1024x1024; 2.run model.predict() to get predictions; 3.merge the predictions of the same large image (perform NMS again); 4. format all predictions as the DOTA evaluation required.The iou threshold is 0.4 and confidence threshold is 0.1. Could you please tell me me where my problem is and how to reproduce the 78 mAP on the DOTA test set? |
Beta Was this translation helpful? Give feedback.
-
|
@Wenshuchen hello! It sounds like you're following the correct steps for evaluation. However, the discrepancy in mAP could be due to several factors. Ensure you're using the latest version of the YOLOv8 package and the same hyperparameters used in our benchmarks. Additionally, double-check your NMS implementation and thresholds. For precise reproduction, you might want to use the exact command |
Beta Was this translation helpful? Give feedback.
-
|
Have you solved your problem?Sent from my iPhoneOn Aug 4, 2024, at 11:21, puppetmonkey ***@***.***> wrote:
I also need this kind of code, but I don't have the time or coding skills. If you could share the completed code, I would be very grateful.
—Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you were mentioned.Message ID: ***@***.***>
|
Beta Was this translation helpful? Give feedback.
-
|
I set the confidence threshold to 0.01 and get mAP 72.26, similar to yours. |
Beta Was this translation helpful? Give feedback.
-
|
@Wenshuchen thank you for sharing your results. It's great to hear that you achieved a similar mAP of 72.26 with a confidence threshold of 0.01. For further details on using YOLOv8 Oriented Bounding Boxes (OBB) models, including training, validation, prediction, and export, you can refer to the comprehensive guide at Ultralytics OBB Documentation. If you have any specific questions or need further assistance, feel free to ask! |
Beta Was this translation helpful? Give feedback.
-
|
My current mAP is 72. What about you?Sent from my iPhoneOn Aug 4, 2024, at 11:21, puppetmonkey ***@***.***> wrote:
I also need this kind of code, but I don't have the time or coding skills. If you could share the completed code, I would be very grateful.
—Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you were mentioned.Message ID: ***@***.***>
|
Beta Was this translation helpful? Give feedback.
-
|
I have already solved this problem, we can communicate. We can communicate privately. You can leave your email address here! |
Beta Was this translation helpful? Give feedback.
-
|
Can you please contact me ? I really want to solve this problem. My email address is 1693330512@qq.com, thank you! |
Beta Was this translation helpful? Give feedback.
-
|
Thank you for reaching out. For assistance with your problem, I recommend referring to our comprehensive documentation on Oriented Bounding Boxes (OBB) at Ultralytics OBB Documentation. This resource provides detailed instructions on training, validation, prediction, and exporting models. If you encounter specific issues, feel free to describe them here, and I'll do my best to assist you. |
Beta Was this translation helpful? Give feedback.
-
|
Hi! my emali address is ***@***.***
Thank you very much!
…---Original---
From: ***@***.***>
Date: Mon, Aug 5, 2024 15:57 PM
To: ***@***.***>;
Cc: ***@***.******@***.***>;
Subject: Re: [ultralytics/ultralytics] tasks/obb/ (Discussion #7974)
I have already solved this problem, we can communicate. We can communicate privately. You can leave your email address here!
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
Beta Was this translation helpful? Give feedback.
-
|
@Wenshuchen thank you for your interest! For any questions or discussions, please use the GitHub Issues or Discussions section. We do not provide private support via email. For more information on using oriented bounding boxes with YOLOv8, please visit our documentation at https://docs.ultralytics.com/tasks/obb/. |
Beta Was this translation helpful? Give feedback.
and others
-
tasks/obb/
Learn how to use oriented object detection models with Ultralytics YOLO. Instructions on training, validation, image prediction, and model export.
https://docs.ultralytics.com/tasks/obb/
Beta Was this translation helpful? Give feedback.
All reactions